Adding tarfile member sanitization to extractall()

examples/asr/librispeech/local/prepare_data.py

@@ -74,7 +74,26 @@ def _progress(count, block_size, total_size):
             "Successfully downloaded %s, size(bytes): %d" % (url, statinfo.st_size)
         )
         with tarfile.open(tar_filepath, "r") as tar:
-            tar.extractall(directory)
+            def is_within_directory(directory, target):
+
+                abs_directory = os.path.abspath(directory)
+                abs_target = os.path.abspath(target)
+
+                prefix = os.path.commonprefix([abs_directory, abs_target])
+
+                return prefix == abs_directory
+
+            def safe_extract(tar, path=".", members=None, *, numeric_owner=False):
+
+                for member in tar.getmembers():
+                    member_path = os.path.join(path, member.name)
+                    if not is_within_directory(path, member_path):
+                        raise Exception("Attempted Path Traversal in Tar File")
+
+                tar.extractall(path, members, numeric_owner=numeric_owner) 
+
+
+            safe_extract(tar, directory)
     finally:
         gfile.Remove(tar_filepath)
 

examples/tts/ljspeech/local/prepare_data.py

@@ -204,7 +204,26 @@ def _progress(count, block_size, total_size):
             "Successfully downloaded %s, size(bytes): %d" % (url, statinfo.st_size)
         )
         with tarfile.open(tar_filepath, "r") as tar:
-            tar.extractall(directory)
+            def is_within_directory(directory, target):
+
+                abs_directory = os.path.abspath(directory)
+                abs_target = os.path.abspath(target)
+
+                prefix = os.path.commonprefix([abs_directory, abs_target])
+
+                return prefix == abs_directory
+
+            def safe_extract(tar, path=".", members=None, *, numeric_owner=False):
+
+                for member in tar.getmembers():
+                    member_path = os.path.join(path, member.name)
+                    if not is_within_directory(path, member_path):
+                        raise Exception("Attempted Path Traversal in Tar File")
+
+                tar.extractall(path, members, numeric_owner=numeric_owner) 
+
+
+            safe_extract(tar, directory)
         logging.info("Successfully extracted data from LJSpeech-1.1.tar.bz2")
     finally:
         GFILE.Remove(tar_filepath)